Learning Interpretable Fair Representations

TL;DR

This paper introduces a framework for learning fair, interpretable data representations that enhance utility and fairness in predictive tasks, enabling better insights and exploration by third parties.

Contribution

It proposes a novel method incorporating interpretable prior knowledge into fair representation learning, improving interpretability, accuracy, and fairness over existing approaches.

Findings

Representations are more interpretable and provide additional insights.

Achieve slightly higher accuracy in downstream tasks.

Attain fairer outcomes compared to state-of-the-art methods.

Abstract

Numerous approaches have been recently proposed for learning fair representations that mitigate unfair outcomes in prediction tasks. A key motivation for these methods is that the representations can be used by third parties with unknown objectives. However, because current fair representations are generally not interpretable, the third party cannot use these fair representations for exploration, or to obtain any additional insights, besides the pre-contracted prediction tasks. Thus, to increase data utility beyond prediction tasks, we argue that the representations need to be fair, yet interpretable. We propose a general framework for learning interpretable fair representations by introducing an interpretable "prior knowledge" during the representation learning process. We implement this idea and conduct experiments with ColorMNIST and Dsprite datasets. The results indicate that in addition to being interpretable, our representations attain slightly higher accuracy and fairer outcomes in a downstream classification task compared to state-of-the-art fair representations.